def evaluate_without_negations(feature_select):
replacer = AntonymReplacer()
posSentences = open('\\resources\\original files\\pos.txt', 'r')
negSentences = open('\\resources\\original files\\neg.txt', 'r')
posSentences = re.split(r'\n', posSentences.read().translate(None, string.punctuation))
negSentences = re.split(r'\n', negSentences.read().translate(None, string.punctuation))
posFeatures = []
negFeatures = []
for i in posSentences:
posWords = re.findall(r"[\w']+|[.,!?;]", i)
posWords = replacer.replace_negations(posWords)
posWords = [feature_select(posWords), 'pos']
posFeatures.append(posWords)
for i in negSentences:
negWords = re.findall(r"[\w']+|[.,!?;]", i)
negWords = replacer.replace_negations(negWords)
negWords = [feature_select(negWords), 'neg']
negFeatures.append(negWords)
posCutoff = int(math.floor(len(posFeatures) * 9 / 10))
negCutoff = int(math.floor(len(negFeatures) * 9 / 10))
trainFeatures = posFeatures[:posCutoff] + negFeatures[:negCutoff]
testFeatures = posFeatures[posCutoff:] + negFeatures[negCutoff:]
# print trainFeatures
classifier = NaiveBayesClassifier.train(trainFeatures)
referenceSets = defaultdict(set)
testSets = defaultdict(set)
for i, (features, label) in enumerate(testFeatures):
referenceSets[label].add(i)
predicted = classifier.classify(features)
testSets[predicted].add(i)
# print testFeatures
accuracy = nltk.classify.util.accuracy(classifier, testFeatures)
print 'train on %d instances, test on %d instances' % (len(trainFeatures), len(testFeatures))
print 'accuracy:', nltk.classify.util.accuracy(classifier, testFeatures)
print 'pos precision:', nltk.metrics.precision(referenceSets['pos'], testSets['pos'])
print 'pos recall:', nltk.metrics.recall(referenceSets['pos'], testSets['pos'])
print 'neg precision:', nltk.metrics.precision(referenceSets['neg'], testSets['neg'])
print 'neg recall:', nltk.metrics.recall(referenceSets['neg'], testSets['neg'])
classifier.show_most_informative_features(10)
return accuracy
def negations(text):
replacer = AntonymReplacer()
sent = text.split()
noneg = replacer.replace_negations(sent)
separator = ' '
out = separator.join(noneg)
return out
def antonym_dealer(document): from replacers import AntonymReplacer replacer = AntonymReplacer() return replacer.replace_negations(document)
df=pd.read_csv(csv_file)
saved_column=df['text']
list1=list(saved_column)
#print (list1)
replacer=AntonymReplacer()
rep1=RepeatReplacer()
rep2=RegexpReplacer()
for i in range(0,len(list1)):
list1[i]=re.sub(r'[^\x00-\x7F]',r' ',list1[i]) #Replacing non-ascii characters with a space
list1[i]=rep2.replace(list1[i]) #texts like can't are converted into can not
list1[i]=list1[i].split() #Splitting each sentence into words
#list1[i]=[w for w in list1[i] if (len(w)>2)] #String length of a word is more than 2
list1[i]=replacer.replace_negations(list1[i]) #Replaces the negative words with antonyms
emo={}
f=open('emotions.txt','r')
for line in f:
line=line.split(',')
emo[line[0]]=line[1].rstrip()
#print(emo)
abb={}
f=open('abb.txt','r')
for line in f:
line=line.split(',')
abb[line[0].lower()]=(line[1].rstrip()).lower()
#print(abb)
#for i in ran
from nltk.tokenize import word_tokenize
from replacers import AntonymReplacer
replacer = AntonymReplacer()
sent = "let's not uglify our code"
print(replacer.replace_negations(word_tokenize(sent)))
print(replacer.replace_negations(word_tokenize("it is not small")))
print(replacer.replace_negations(word_tokenize("it is not high")))
print(replacer.replace_negations(word_tokenize("it is not fine")))
def negations(text):
sent = text.split()
noneg = replacer.replace_negations(sent)
separator = ' '
out = separator.join(noneg)
return out
replacer = AntonymReplacer()
#replacer.replace('good')
#replacer.replace('uglify')
sent = ['good', 'do', 'not', 'go']
aaa = replacer.replace_negations(sent)
L = pd.read_csv("hip_hop_nocontracted_v4_lowercase.csv", index_col=0)
separator = ' '
bbb = separator.join(aaa)
L3 = L
L3['Lyrics'] = L3['Lyrics'].apply(negations)
def negations(text):
sent = text.split()
noneg = replacer.replace_negations(sent)